query_knowledgeLABSCO SUMMARY
Compliance you can look up at the moment the agent acts.
The unit of retrieval is a gate rather than an article: a record arrives with its GDPR or EU AI Act citation and a stated route for the pass and the fail case, which is what makes it usable inside a run instead of at review time.
What it is
A hosted compliance library an agent queries at runtime. Modules are mapped to EU AI Act articles, and each one is served in four layers — logic, directive, skill and action — so a retrieval returns pass/fail gates carrying their statutory citation, not a paragraph to interpret.
What you get
- query_knowledge walks the library by node ID — the vertical, then the module, then the layer you want
- Logic layers come back as JSON rulesets: every record carries its source citation and an explicit if_true / if_false route
- get_trial_key issues a key against an agent ID you name, with no signup form in the way
- check_status reports the API version and which verticals are currently live
- join_waitlist registers you for a vertical membership; register_interest signals demand for one that does not exist yet
- submit_pov sends a Proof of Value back after you have explored the trial; submit_referral records a referral against a membership key
- Streamable HTTP at one endpoint, so any client that speaks it connects without an SDK
Requirements
Nothing to install — point a Streamable HTTP client at https://api.agent-module.dev/mcp. The root index is open; the content layers take a key, passed as a token parameter or an X-Agent-Module-Key header, and get_trial_key issues one.
Setup effort
Paste a URL — add the endpoint to your client
USE CASES
01
Grounding an agent in the obligations that apply to it
Start at the root index, drill into the module covering the obligation in question, and pull its logic layer so the rules arrive as cited records.
02
Gating an action before it runs
Fetch the logic layer for the relevant module and route on its if_true and if_false branches, so an out-of-scope action halts and escalates instead of proceeding.
03
Trying it before committing to a membership
Issue a trial key against your agent ID, read across the logic, directive, skill and action layers, then send back a Proof of Value with your own confidence score.
04
Checking what exists before planning around it
Read the API version and the list of live verticals, then join the waitlist for one that is running or signal demand for one that is not built yet.
7 tools
Listed in project docs. Your client may show a different list.
get_trial_keycheck_statusjoin_waitlistregister_interestsubmit_povsubmit_referralBEFORE YOU INSTALL
What to know first
Tools you get
7 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
Where it runs
All 3 documented clients connect to a hosted endpoint.
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://api.agent-module.dev/mcpMCP Clients
Claude Code
CLAUDE CODE · JSON
{
"mcpServers": {
"agent-module": {
"type": "http",
"url": "https://api.agent-module.dev/mcp"
}
}
}Cursor
CURSOR · JSON
{
"mcpServers": {
"agent-module": {
"type": "streamable-http",
"url": "https://api.agent-module.dev/mcp"
}
}
}Any MCP client
ANY MCP CLIENT · JSON
{
"mcpServers": {
"agent-module": {
"type": "streamable-http",
"url": "https://api.agent-module.dev/mcp"
}
}
}Clients spell the "type" value differently: Claude Code and VS Code use "http", Cline uses "streamableHttp", and Roo Code uses "streamable-http". Claude Desktop does not accept a URL entry in its config file; remote servers go under Settings → Connectors.
